merlyn/server
Marcello Fitton 1ccf468158
fix: correct TPS calculation for Generic OpenAI provider with llama.cpp (#4981)
* add check for timings field on final chunk to override usage data

* refactor: extract llama.cpp timings into reusable private method

Move timings extraction into #extractTimings so it can be shared
by both streaming (handleStream) and non-streaming (getChatCompletion)
code paths.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* lint and cleanup

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Timothy Carambat <rambat1010@gmail.com>
2026-02-12 14:40:35 -08:00
..
__tests__ Refine and Standardize Username Constraints (#4828) 2026-01-26 16:18:11 -08:00
endpoints refactor: Migrate system preferences to field-based endpoint and remove deprecated endpoint (#4958) 2026-02-09 12:48:48 -08:00
jobs linting + tolerate folder deletion for bad ParsedFile inserts 2026-02-08 14:35:50 -08:00
middleware Add HTTP request/response logging middleware for development mode (#4425) 2025-09-29 13:33:15 -07:00
models set embedder output dimensions for LocalAI and Gemini (gemini-embedding-001) (#4980) 2026-02-10 08:28:34 -08:00
prisma Web push notifications (#4942) 2026-02-02 10:56:58 -08:00
storage normalize logo wordmark 2026-02-11 08:53:44 -08:00
swagger feat: add base64 document attachment support to API chat endpoints (#4672) 2025-11-24 15:48:44 -08:00
utils fix: correct TPS calculation for Generic OpenAI provider with llama.cpp (#4981) 2026-02-12 14:40:35 -08:00
.env.example Update LMStudio LLM & Embedder for API token (#4948) 2026-01-30 11:13:32 -08:00
.flowconfig devcontainer v1 (#297) 2024-01-08 15:31:06 -08:00
.gitignore Web push notifications (#4942) 2026-02-02 10:56:58 -08:00
.nvmrc dev build with new epub2 build target and remove patch work (#4694) 2025-11-26 17:36:34 -08:00
index.js Web push notifications (#4942) 2026-02-02 10:56:58 -08:00
jsconfig.json devcontainer v1 (#297) 2024-01-08 15:31:06 -08:00
nodemon.json Full developer api (#221) 2023-08-23 19:15:07 -07:00
package.json chore: bump ollama SDK from 0.5.10 to 0.6.3 (#4977) 2026-02-09 15:34:31 -08:00
yarn.lock chore: bump ollama SDK from 0.5.10 to 0.6.3 (#4977) 2026-02-09 15:34:31 -08:00